video_core: less waiting on the GPU caches' locks

- The texture and buffer caches' mutexes spin briefly before sleeping
  (Common::SpinRecursiveMutex): the GPU thread, the fencing thread and
  CPU write traps take them tens of thousands of times a second for
  microseconds, and a sleeping waiter's wake-up took longer than that.
  Title 1's GPU thread slept 7.7% of its time there, now 3.7%.
- Fences commit and pop texture and buffer downloads separately, and
  only when there are any (one fence per compute dispatch in Switch 2
  titles): the fencing thread no longer holds both caches while it
  copies buffer downloads.
- Inline uploads and pre-draw invalidation take the caches one at a
  time again: holding one while std::lock waited for the other waited
  longer.

1 files changed, 5 insertions, 0 deletions

diff --git a/src/video_core/texture_cache/texture_cache.h b/src/video_core/texture_cache/texture_cache.h
index 13dfbba20e..fb8adef161 100644
--- a/src/video_core/texture_cache/texture_cache.h
+++ b/src/video_core/texture_cache/texture_cache.h
@@ -990,6 +990,11 @@ bool TextureCache<P>::HasUncommittedFlushes() const noexcept {
 }
 
 template <class P>
+bool TextureCache<P>::HasAsyncFlushWork() const noexcept {
+    return !uncommitted_downloads.empty() || !uncommitted_async_buffers.empty();
+}
+
+template <class P>
 bool TextureCache<P>::ShouldWaitAsyncFlushes() const noexcept {
     return !committed_downloads.empty() && !committed_downloads.front().empty();
 }